← Leaderboard
Voxtral Small 24B 2507
Open source
Self-hostable
Free to run
Mistral
Open license
text
audio
Released 1y agoAvg score
50.2
/ 100 · not enough data for the index
Context
33k
Output limit
26k
Input price
$0.10 /M
Output price
$0.30 /M
Parameters
24.3B
Est. VRAM (Q4)
~14.6 GB
Price from the model maker's own API, verified 8h ago · cached input $0.01 /M
Added automatically from the public model catalog. Family and licence details are not curated yet; benchmark scores appear as upstream leaderboards list this model.
Benchmarks
performance
Output SpeedN/A
tok/sMedian output speed in tokens per second over the last 14 days on the model maker's own API, measured nightly with a fixed ~800-token prompt and ~250-token answer. Models not yet probed fall back to a dated manual figure. Higher is faster.
Time to First TokenN/A
msMedian time from request to first streamed token in milliseconds over the last 14 days on the model maker's own API, using the same nightly probe prompt. Lower is snappier; reasoning models are penalised here because they think before talking.
Reliability monitor
Loading drift signal…
Hosted endpoints
| Host | Input $/M | Output $/M | Context | Speed | TTFT | Uptime 24h | Quant |
|---|---|---|---|---|---|---|---|
| Host 42maker's API | $0.10 | $0.30 | 33k | 179 tok/s | 0.65 s | 99.9% | unknown |
| Host 40maker's API | $0.10 | $0.30 | 33k | — | — | 100.0% | unknown |
| Host 41maker's API | $0.11 | $0.33 | 32k | — | — | 100.0% | unknown |
Anonymised third-party hosts. Sorted by lowest output price. Speed and time to first token are medians from our nightly probe where measured; uptime is the catalog's 24-hour figure.